Instructor: Robert C. Berwick	TA: Sourabh Niyogi
Email: berwick@ai.mit.edu	Email: niyogi@mit.edu; http://www.mit.edu/~niyogi/
Office: 35-423	Office: 35-419
Phone: (617) 253-8918	Phone: (617) 253-7255
Office hours: Weds 12-2 and by appointment	Office hours: T12-2 (35-419)

• 04/25/02    Lecture 18 concluding lecture on determiners here   [pdf]
• 04/23/02    Lecture 17 on determiners here   [pdf]
• 04/23/02    Lecture 16 on lexical semantics I here [pdf]
• 04/23/02    Lecture 15 on semantic interpretation here [pdf]
• 04/23/02    Lecture 14 on semantic interpretation here [pdf]
• 04/09/02    Project ideas for final project here
• 04/09/02    For more on semantic interpretation, see notes5.pdf, here
• 04/08/02    Note: Lab 4 handed out here, due next Wednesday
• 04/03/02    Note: Lab 3 will be due at the end of today (midnight). Lab 4 will be posted then, due next Wednesday
• 04/03/02    Lecture 13 (probabilistic grammars II & semantic interp.) posted here.  [pdf]
• 04/03/02    Lecture 12 (probabilistic grammars) posted  here.  [pdf]
• 03/31/02    The pdf file for Lab 3 was apparently damaged wrt printing; this is now fixed.  Consequently, I have changed the due date for Lab 3 to Wednesday, April 3.
• 03/21/02    Sourabh is away this week; I will hold extended office hours & set up group meetings in his stead

Older messages: (messages older than a month can be found on a link here.)
• 03/21/02    Have a good Spring Break!  See you on April Fool's Day...
• 03/21/02    Lecture 11 (feature grammars) posted  here.  [pdf]
• 03/18/02    Lecture 10 (writing grammars) posted  here.  [pdf]
• 03/18/02    Lab 3 (parsing) now posted (pdf) here.  Due April 1. Please also see the parser documentation here and the guide to the PennTreeBank annotation here.  (Caution: this last document is very long.)  For a very simple introduction to phrases in English, read this.
• 03/15/02    Lectures 8 and 9 are available as slides here and here.Please also read notes 4.
• 03/15/02    First 'affinity group' meetings will be next week - stay tuned!
• 03/10/02    Reminder: Lab 2 is due this Wednesday.
• 03/07/02    For fun: you can play the 'Shannon game' & estimate the entropy of English here. (Java applet).  Kudos to Florian Wolf for finding this neat app.
• 03/06/02    Lab 2 (complete) available here. Note: this lab now has only two parts.
• 03/03/02    NOTE: Lab 1b is due this monday (March 4) & Lab 2 will be handed out then as well, due 1 week later (March 13).
• 03/01/02    Demo of combination part of speech tagger & 'chunking' parser here.
• 03/01/02    Lecture 7 slides available herepdf

Prerequisites & Relation to Other Courses:

The material covered in this course is selected in such a way that at its completion you should be able to understand current papers in the field of Natural Language Processing (NLP).   No background in NLP is necessary.  All lectures will be published on this page in powerpoint (ppt), Adobe pdf (pdf) and postscript (ps) form; the latter two are more useful for downloading and printing. If you do not have Adobe Acrobat Reader for pdf files on your computer, you can download it from www.adobe.com.

Readings:

Required (available at the MIT Coop,  and through Quantum books):

 

Jurafsky, D. and Martin, J.H., Speech and Language Processing,        PrenticeHall: 2000.  ISBN: 0130950696

Recommended & Reference Readings (all on library reserve):

 

Manning, C. D. and H. Schütze: Foundations of Statistical Natural Language Processing. The MIT Press. 1999. ISBN 0-262-13360-1.


 

Barton, E., Berwick, R., & Ristad, E.. Computational Complexity and Natural Language: The MIT Press. 1987. ISBN 0-26-02266-4. (Sorry no real cover picture available.)

Allen, J.: Natural Language Understanding. The Benajmins/Cummings Publishing Company Inc. 1994. ISBN 0-8053-0334-0.

Brady, J & Berwick, R.: Computational Models of Discourse. The MIT Press, 1983. ISBN-0-262-02183-8 .

Charniak, E.: Statistical Language Learning. The MIT Press. 1996. ISBN 0-262-53141-0.

• Proceedings of major conferences (related to Natural Language Processing):
• ACL (Association of Computational Linguistics)
• European Chapter of the ACL
• COLING (International Committee of Computational Linguistics)
• ANLP (Applied Natural Language Processing, by ACL)
• ACL SIGDAT, SIGNLL other SIG (Special Interest Groups) Workhops, such as WVLC (Workshop on Very Large Corpora)
• EMNLP (Empirical Methods in Natural Language Processing
• DARPA HLT (Defense Advanced Research Project Agency Human Language Technology Workshops)

Assignments & Due Dates:

Assignments

This course is lab-oriented; that is, the work of the course is done via a series of laboratory exercises.  These will be handed out once approximately every two weeks.  There are no exams, in particular, there will be no final exam.  The final project will involve an element of non-determinism, i.e., so-called 'free will',  in that you will be able to choose your own project and combine elements from the previous laboratories, or do something completely new.  For the final project, we will have people work in teams of 2 or 3 (but not more).

The laboratory exercises are designed to be carried out on Athena.  If you are clever and adventuresome, you are certainly free to download the software used and get it running on your own PC/laptop, but this must be own 'your own nickel' - i.e., we cannot guarantee that you will succeed, nor can we offer technical support to do so.

Turning in the Assignments

When

The assignments are due at the end of class on the due date, i.e., 11:30am.

Policies

Lateness

You have up to 30 (thirty) late days to use up, that can be distributed among your laboratory projects. However, the last project must be turned during the last week of class (5/13-5/17), even if you have not used all of your days by then.

Once you use up your late days, late projects will not earn any points, even though they might be considered in borderline cases for the final grade. Thus try to turn in all projects, even though you might feel they are not to be counted. If you do not turn in a final (joint) project, you will receive an I (incomplete) for the class, and will have to make this up by next term (the incomplete will note that 80% of the coursework has been completed).

Cooperative Work and Plagiarism

Cooperative work is strongly encouraged; you are free to work together on laboratory assignments.  However, aside from the last project, you must write up and turn in your own work.  Please write the names of the people with whom you worked at the top of the first page.  Exact copies of laboratory reports will not be acceptable. (Something other than your name and those of your co-workers must be different!)  The aim of the course (and its pedagogical philosophy) is to learn about natural language processing.  You will learn more if you actually do the laboratory assignments.

The Assignments

Additional resources:

• Lab 1a: englex.tar.gz. (english rules and lexicon); List of names to use to test Soundex here.
• Lab 2: web version of Brill tagger with tracing option (watch out: default language is Swedish): here.
• Guest athena form: Please give sourabh your email name so he can email Athena and have the account set up for you

Tentative Course Schedule:

Grading Weights: